Downloads · 30 days
0
diff_lora-r8_anisora_wan2.1_i2v
nomadoor/diff_lora-r8_anisora_wan2.1_i2v
diff_lora-r8_anisora_wan2.1_i2v is a machine learning model from nomadoor. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This is a LoRA (Low-Rank Adaptation) model representing the raw parameter difference between the following two video generation models:
Access
Public
Updated Jul 17, 2025
Repo size
100 MB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors100 MB · 100%
At a glance
- Access
- Public
- Created
- Jul 17, 2025
- Updated
- Jul 17, 2025
- SHA
- 042f52db
Model card
From the Hugging Face model README
diff_lora-r8_anisora_wan2.1_i2v_480p14B_fp8e4m3fn
This is a LoRA (Low-Rank Adaptation) model representing the raw parameter difference between the following two video generation models:
-
Finetuned model (Anisora):
Wan2_1-Anisora-I2V-480P-14B_fp8_e4m3fn.safetensors -
Base pretrained model:
wan2.1_i2v_480p_14B_fp8_e4m3fn.safetensors
❗ Disclaimer
- This LoRA was generated by taking the direct parameter difference between the two
.safetensorsfiles. - No additional training, fine-tuning, or quality filtering has been applied.
- While it can be used for
text2videoand related pipelines (e.g. with ComfyUI), its behavior and correctness are not guaranteed. - Treat this as a technical test or experimental reference only.
📦 Details
| Field | Value |
|---|---|
| LoRA Rank | 8 |
| Base Model | Wan2.1 I2V 480p 14B fp8 e4m3fn |
| Finetuned Target | Wan2.1-Anisora-I2V |
| Precision | fp8 (e4m3fn) |
| Format | .safetensors |
- Created
- Jul 17, 2025
- Updated
- Jul 17, 2025